© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13699
    Prev
    Next
    INDEX
    Explanations

    the first-person perspective and attempts to give advice

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     picioare
    -0.59
    DataAnnotations
    -0.57
     gouvernements
    -0.56
     bonté
    -0.55
     culoare
    -0.54
     שוליים
    -0.53
     schimb
    -0.52
     arquitetura
    -0.52
     abandonné
    -0.52
     vrea
    -0.51
    POSITIVE LOGITS
     ویکی‌آمباردا
    0.62
    Хьажоргаш
    0.61
     يتيمه
    0.60
    XmlType
    0.55
    irement
    0.55
     minus
    0.54
    日閲覧
    0.52
    roxene
    0.52
    queryInterface
    0.52
    HasAnnotation
    0.51
    Activations Density 2.633%

    No Known Activations